Combining citizen science and AI to predict Harmful Algal Blooms (HABs) in the Baltic Sea
Citizen science has become a powerful tool to empower and educate citizens to participate in challenges facing their communities by contributing valuable data for advanced analytics. As part of the third cycle of ODF Sweden, “The HAB/Killer Algae Challenge”, we have created a flexible workflow with an integrated GUI for reporting and data acquisition of HABs, in collaboration with Maranics and regional authorities in Stockholm and Västerbotten. We have also successfully developed the first iteration ML model to identify blooms from images in a mobile application. This presentation will highlight some of the challenges and outcomes from our second season of data collection and its impact on the community, and look forward to what we aim to accomplish in the upcoming season.
About the speaker
Jurie (Jannes) Germishuys is a data scientist and engineer with a background in actuarial science, experience in natural language processing (NLP), probabilistic graphical models and financial
modelling. He has built scalable pipelines and machine learning deployments for deep learning analytics and commercial AI product development use cases, particularly in NLP and computer vision. His experience stretches from insurance and banking to telecommunications and water utilities. He has a strong interest in furthering the field of artificial intelligence and using algorithmic problem-solving to create lasting value.
About Ocean Data Factory Sweden
The mission of ODF Sweden is to enable data-driven innovation by both commercial and non-commercial actors to ensure that the ocean and its resources are managed in the best possible and most sustainable way. ODF runs several in-house innovation projects, for example, the Koster Challenge, that combines citizen science with AI to explore Sweden’s marine biodiversity. https://oceandatafactory.se/what-we-do/innovation/